VPFL: A verifiable privacy-preserving federated learning scheme for edge computing systems

Abstract

Federated learning for edge computing is a promising solution in the data booming era, which leverages the computation ability of each edge device to train local models and only shares the model gradients to the central server. However, the frequently transmitted local gradients could also leak the participants’ private data. To protect the privacy of local training data, lots of cryptographic-based Privacy-Preserving Federated Learning (PPFL) schemes have been proposed. However, due to the constrained resource nature of mobile devices and complex cryptographic operations, traditional PPFL schemes fail to provide efficient data confidentiality and lightweight integrity verification simultaneously. To tackle this problem, we propose a Verifiable Privacy-preserving Federated Learning scheme (VPFL) for edge computing systems to prevent local gradients from leaking over the transmission stage. Firstly, we combine the Distributed Selective Stochastic Gradient Descent (DSSGD) method with Paillier homomorphic cryptosystem to achieve the distributed encryption functionality, so as to reduce the computation cost of the complex cryptosystem. Secondly, we further present an online/offline signature method to realize the lightweight gradients integrity verification, where the offline part can be securely outsourced to the edge server. Comprehensive security analysis demonstrates the proposed VPFL can achieve data confidentiality, authentication, and integrity. At last, we evaluate both communication overhead and computation cost of the proposed VPFL scheme, the experimental results have shown VPFL has low computation costs and communication overheads while maintaining high training accuracy.

Keywords

• Federated learning
• Edge computing
• Privacy-preserving
• Verifiable aggregation
• Homomorphic cryptosystem